Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bostonaholic/team --skill verifying-uxgit clone --depth 1 https://github.com/bostonaholic/teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bostonaholic/team/verifying-ux)<a href="https://agentmods.dev/skills/bostonaholic/team/verifying-ux"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/verifying-ux/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bostonaholic/team/verifying-ux"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/verifying-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00704 |
| Opus 5 | $0.00011 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
verifying-ux scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
use `curl` on home and changed routes, inspect errors, capture screenshots, How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying UX
Boot and use the application as a user. Read references/procedure.md before verification; it owns the detailed UI/API checks, manifest body, skip handling, and report rules.
Detection and lifecycle
- UI: rendered pages/components/routes. Start the dev server, wait until ready,
use
curlon home and changed routes, inspect errors, capture screenshots, then stop the server. - API-only: start it, use real
curlrequests for success, headers, bodies, invalid input, missing auth/parameters, and not-found behavior, then stop it. - Library: report live verification not applicable.
ALWAYS stop the dev server, including after failure. Do not change code or test unrelated behavior. A server that is not ready within 60 seconds is the primary finding. Keep commands and output for reproduction.
Screenshot Capture (UI projects)
Capture while the server runs and only when both conditions hold: project type
is UI and the full branch diff touches components, templates, pages, routes, or
styles. Use git diff $(git merge-base <base-branch> HEAD)..HEAD; resolve base
with git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@',
fallback main. Otherwise create no screenshots directory or manifest.
Wipe <artifact-dir>/screenshots/ before capture. Seed with the project's
mechanism when available; otherwise capture with seeded: false and seed_note.
Use Playwright CLI through Bash. Capture viewport PNGs for affected populated,
empty, and error states as <NN>-<route-slug>-<state>.png.
Never capture secrets or real PII. Skip auth-only routes. Limits: 10 shots per round, 5-minute total, 30s per-shot timeout. Record timeouts and continue. Screenshot failure is Could Improve, never REQUEST CHANGES.
Statuses:
captured: every planned shot exists.partial: some shots skipped.skipped-server-start: server unavailable.skipped-no-tool: Playwright or Chromium unavailable.
Write <artifact-dir>/screenshots/manifest.md with a quoted heredoc delimiter
(<<'EOF'). Pass every variable route, path, caption, and note as a separate or
single-quoted argument; never interpolate into a command string.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · -83 lines · -31 tokens per session c1da892fa72c
- 7d ago First seen · 156 lines · 53 tokens per session scan A a702394d954f
verifying-ux is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 704 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.